rl and rsrl
These are competitors—both are general-purpose reinforcement learning frameworks in Rust that serve the same use case, with rsrl being more mature and widely adopted (4x the stars, 3x the downloads).
About rl
benbaarber/rl
A rust reinforcement learning library
About rsrl
tspooner/rsrl
A fast, safe and easy to use reinforcement learning framework in Rust.
Provides modular RL algorithm implementations (Q-Learning, policy gradients) with linear function approximators and basis projections (Fourier, RBF) for continuous state spaces. Built on `ndarray` with optional BLAS acceleration for efficient numerical computation. Designed around composable traits for agents, policies, and environments, enabling rapid prototyping of RL experiments.
Scores updated daily from GitHub, PyPI, and npm data. How scores work